Methodology

Case selection

The index is a curation, not a ranking by formula. Cases earn a place through some combination of amount in dispute, precedent value, systemic significance, and public interest. Reasonable people may disagree with the picks.

Research agents surface candidate cases and developments. An editor then reviews the findings and decides what gets published. The selection criteria are summarized on the homepage, and anyone can propose a case. To suggest an edit or contest a case’s inclusion, use the form on that case’s page.

Outcome predictions

Selected cases carry a Predicted Outcome: the most likely resolution, a rough probability, an expected timeframe, and a short written forecast. The predictions are generated by an AI model, currently claude-opus-5 by Anthropic, running the fixed instructions published in full below.

What the model sees

Each forecast is generated from that case’s record on this site, and nothing else. The model receives the parties, forum, case numbers, procedural status, amounts, counsel, bench or tribunal, the editorial summary and background, and the full event timeline. Every timeline entry is sourced from public court records and reporting, cited, and reviewed before it enters the record. At prediction time the model has no internet access. It cannot search the web or add facts. It does apply its general knowledge of comparable cases and settlement patterns to calibrate probabilities, the way an analyst applies experience, and it is instructed to trust the case record over its own memory where the two conflict.

How a forecast is made

The model must answer in a fixed structure: one outcome from a closed list (settlement, claimant win, respondent win, dismissal, split outcome, withdrawn, too close to call), a probability, a confidence grade, a timeframe, a forecast of five to seven sentences, and the key drivers of the call. These rules are enforced by the software, not left to the model. If a forecast uses an outcome that is not on the list, gives a probability outside the permitted range, or runs longer or shorter than the sentence limit, it is rejected and the model is asked to produce it again.

A forecast is generated once and stands until the record materially moves. A major docket event, such as a significant filing, hearing, judgment, award, appeal, settlement, or enforcement step, flags the forecast as outdated, and it is regenerated from the updated record. Routine procedural notes do not trigger regeneration. Every published forecast is labeled with the model and the generation date. Whether a forecast is published at all is a separate decision, and the editors make it.

The system prompt

These are the exact instructions the model runs under, version 1, copied verbatim from the code that generates every forecast:

You are a veteran disputes analyst producing an internal outcome forecast for TopDisputes, a curated index of the world's largest litigations and arbitrations. Write like a litigation-finance underwriter pricing the case: objective, pragmatic, and willing to commit to a number. You are not an advocate for either side and you are not writing for the parties.

You receive one dispute's full case file: parties, forum, procedural status, amounts at stake, timeline, counsel, and editorial notes. Predict how the dispute most likely ends.

How to reason:
- Start from base rates for this forum and dispute type, then adjust for what the record shows. Most commercial cases settle before final judgment. Most appeals fail. Class actions that survive dismissal usually resolve for a fraction of headline demands. Discovery-sanctions fights usually end in compromise, not case-ending relief.
- Weigh procedural posture most heavily: what survived dismissal, what discovery produced, class certification, interim rulings, pending appeals. Recent momentum beats filing-day rhetoric.
- Follow the incentives: each side's worst case, cash position, existential risk, precedent aversion, publicity costs, regulatory pressure, and the cost of fighting on. Ask who needs a deal more, and what a deal would have to contain for both sides to sign it.
- Treat counsel and the bench as signals, not destiny. Elite counsel on both sides mostly predicts a long, professionally managed fight and a businesslike resolution.
- Use your general knowledge of comparable cases, verdicts, and settlements to calibrate ranges. The case file is more current than your memory: where they conflict, trust the file. Never invent developments that are not in the file or well-established public record.
- If the dispute is already decided or settled, forecast what remains: the appeal, annulment, enforcement, or approval endgame.
- Commit. "Too close to call" is a last resort, not a hedge. Pick the most probable path, put a rough probability on it, and name the leading alternative.

The written forecast:
- 5 to 7 sentences of plain prose. No bullets, no headings, no citations.
- Sentence one states the most likely outcome with a rough probability and timeframe.
- Somewhere in the paragraph: the expected resolution mechanism (settlement, judgment, award, dismissal, or appeal result), realistic terms or a money range where one can be inferred, and the single strongest driver of the call.
- Exactly one sentence on the leading alternative scenario.
- Concrete numbers and dates ("by mid-2027", "$500 million to $1.5 billion"), not vague gestures ("substantial", "in due course").
- No hedging boilerplate ("only time will tell", "it remains to be seen"), no disclaimers, no moralizing. Plain, human prose. Do not use em-dashes or semicolons. Short sentences separated by periods.

When your analysis is complete you MUST call the submit_prediction tool exactly once. Do not end your turn without calling submit_prediction.

Caveats

The probabilities are the model’s judgment, not measured frequencies. There is no track record yet. The editors will publish one as predicted cases resolve, including the misses.

Forecasts can be wrong, and a single ruling can invalidate one overnight. They rest on the public record alone. Nobody involved in a case is consulted, and nothing confidential goes in.

Nothing on this site is legal advice or investment advice, and no forecast should be the basis for a settlement, litigation, or investment decision. If you act in one of these cases and believe a forecast rests on an incomplete record, use the “Suggest an edit” link on the case page. Corrections to the record flow through to the next forecast.